Download Data Mining 2016

Data Mining 2016
Martti Juhola
1
Lectures and exercises
Martti Juhola:
- advanced study course 5 ECTS
- lectures on the 12th January in Pinni B 3107, then in Pinni B1084, on Tuesday
at 10 – 12, from the 19th January to the 16th February, and
on the 13th January in Pinni 1097, then in Pinni B1084, on Wednesday at 10 –
12, from the 20th January to the 17th February
- 12 lectures, 24 h
Jyrki Rasku:
- weekly exercises in Pinni B0039, on Thursday at 12 – 14, from the 21st
January to the 18th February
- 5 times, 10 h
2
To pass the course:
(1) at least 30% of weekly exercises made; if made more, additional scores
can be obtained when one makes more of all weekly exercises than 30 %,
additional scores [0,5] are given as follows: 30 %, 0; 41 %, 1; 52 %,
2; 63 %, 3; 74 %, 4; 85 %, 5 scores (at least 30% of all weekly
exercises have to completed)
(2) the examination is passed, when scores are obtained from [12,30];
exercise scores are added to the examination scores.
Examinations: the 17th March and 7th April, 2016, at 16-20, in D10a+b.
3
Literature:
Dorian Pyle: Data Preparation for Data Mining, Morgan Kaufmann (Elsevier),
1999
David Hand, Heikki Mannila and Padhraic Smyth: Principles of Data Mining,
MIT Press, 2001
Margaret H. Dunham: Data Mining, Introductory and Advanced Topics,
Pearson Education Inc., 2003
Ian H. Witten, Eibe Frank, Mark A. Hall: Data Mining, Practical Machine
Learning Tools and Techniques (third edition), 2011
Krysztof J. Cios, Witold Pedrycz, Roman W. Swiniarski and Lukasz A. Kurgan:
Data Mining, A Knowledge Discovery Approach, Springer, 2007
Some journal articles.
4
Notes
The content of the current course considers mostly preparation or
preprocessing of data for mining for two reasons. Preprocessing is in a
significant role to obtain as good results as possible in data mining. Machine
learning algorithms needed for explorative data analysis, prediction,
classification and clustering have a minor role in this course, beause they will be
the content of course Machine Learning Algorithms (period IV, 2016) and
probably that of Neurocomputing (spring term 2017).
Since this is the first presentation of the current course, some
appear.
may
5